Precise and dense AI-based mobile 3D reconstruction of indoor scenes by camera-lidar fusion and odometry
| cam.depositDate | 2022-04-06 | |
| cam.orpheus.counter | 33 | |
| cam.orpheus.success | Wed May 24 18:39:00 UTC 2023 - Embargo updated | |
| dc.contributor.author | Trzeciak, Maciej | |
| dc.contributor.author | Brilakis, Ioannis | |
| dc.contributor.orcid | Trzeciak, Maciej [0000-0001-8188-487X] | |
| dc.contributor.orcid | Brilakis, Ioannis [0000-0003-1829-2083] | |
| dc.date.accessioned | 2022-06-01T23:30:05Z | |
| dc.date.available | 2022-06-01T23:30:05Z | |
| dc.date.issued | 2022-07-24 | |
| dc.date.updated | 2022-04-06T13:29:19Z | |
| dc.description.abstract | We propose a mobile 3D reconstruction method for improving the precision and density of point clouds. It is suitable for hand-held scanners comprised of a colour camera and a lidar. We fuse time-synchronized and spatially registered images and lidar sweeps using deep learning techniques into dense scans, which are then used for progressive reconstruction in an odometry-like manner. We build a prototypic scanner and test our method in an indoor case-study. The results show that our pipeline outperforms reconstructions by other devices and methods, yielding relatively denser and detail-preserving point clouds with a 46% reduction in noise of reconstructed planar surfaces. | |
| dc.identifier.doi | 10.17863/CAM.85071 | |
| dc.identifier.issn | 2684-1150 | |
| dc.identifier.uri | https://www.repository.cam.ac.uk/handle/1810/337665 | |
| dc.language.iso | eng | |
| dc.publisher | University of Turin | |
| dc.publisher.department | Department of Engineering Student | |
| dc.publisher.url | http://dx.doi.org/10.35490/ec3.2022.150 | |
| dc.rights | All Rights Reserved | |
| dc.rights.uri | http://www.rioxx.net/licenses/all-rights-reserved | |
| dc.subject | 4013 Geomatic Engineering | |
| dc.subject | 46 Information and Computing Sciences | |
| dc.subject | 40 Engineering | |
| dc.title | Precise and dense AI-based mobile 3D reconstruction of indoor scenes by camera-lidar fusion and odometry | |
| dc.type | Conference Object | |
| dcterms.dateAccepted | 2022-03-19 | |
| prism.publicationName | Proceedings of the 2022 European Conference on Computing in Construction | |
| pubs.conference-finish-date | 2022-06-26 | |
| pubs.conference-name | 2022 European Conference on Computing in Construction | |
| pubs.conference-start-date | 2022-07-24 | |
| pubs.funder-project-id | EPSRC (EP/V056441/1) | |
| pubs.licence-display-name | Apollo Repository Deposit Licence Agreement | |
| pubs.licence-identifier | apollo-deposit-licence-2-1 | |
| rioxxterms.version | AM | |
| rioxxterms.versionofrecord | 10.35490/ec3.2022.150 |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- 220126_final.pdf
- Size:
- 630.35 KB
- Format:
- Adobe Portable Document Format
- Description:
- Accepted version
- Licence
- http://www.rioxx.net/licenses/all-rights-reserved